
Yongzhi Su
E-Mail: | yongzhi.su@dfki.de |
---|---|
Position: | Researcher |
Phone: | +49 631 20575-3416 |
I am currently a PhD student at TU Kaiserslautern, advised by Prof. Dr. Didier Stricker and Dr. Jason Rambach. I also visited the CAMP Chair at TU Munich as a visiting researcher, supervised by Prof. Dr. Nassir Navab and PD Dr. Federico Tombari.
My research interests are computer vision and deep learning, especially in object pose estimation and its applications. Our CVPR paper ‘ZebraPose’ shows a major improvement over the stateof-the-art on several datasets. Moreover, ‘ZebraPose’ also wins awards in the BOP 6DoF pose estimation workshop of ECCV2022.
I also contribute to the academic community by serving as a teaching assistant for lectures, student projects and theses, as well as a reviewer for CVPR, IROS, RA-L, and ISMAR.
U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds
In: IEEE/CVF (Hrsg.). Proceedings of the. International Conference on Computer Vision (ICCV-2023), October 2-6, Paris, France, IEEE/CVF, 2023.
Details
| Link 1
| Link 2
OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection
In: IEEE Robotics and Automation Letters (RA-L), Vol. 8, Pages 1327-1334, IEEE, 3/2023.
Details
| Link 1
ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation
IEEE/CVF. International Conference on Computer Vision and Pattern Recognition (CVPR-2022) June 19-24 New Orleans Louisiana United States IEEE/CVF 2022 .
Details
| Link 1
SynPo-Net--Accurate and Fast CNN-Based 6DoF Object Pose Estimation Using Synthetic Training
Special Issue Object Tracking and Motion Analysis, Sensors - Open Access Journal (Sensors) 21 Seite 300 MDPI 2021 .
Details
| Link 1
TGA: Two-level Group Attention for Assembly State Detection
Proceedings of the 19th IEEE ISMAR. IEEE International Symposium on Mixed and Augmented Reality (ISMAR-2020) November 9-13 Recife/Porto de Galinhas Brazil IEEE 2020 .
Details
| Link 1
A Shape Completion Component for Monocular Non-Rigid SLAM
Proceedings of the 18th IEEE ISMAR. IEEE International Symposium on Mixed and Augmented Reality (ISMAR-2019) October 14-18 Beijing China IEEE 2019 .
Details
| Link 1
Deep Multi-State Object Pose Estimation for Augmented Reality Assembly
Proceedings of the 18th IEEE ISMAR. IEEE International Symposium on Mixed and Augmented Reality (ISMAR-2019) October 14-18 Beijing China IEEE 2019 .
Details
| Link 1